[PATCH v1 1/1] memory tier: acpi/hmat: create CPUless memory tiers after obtaining HMAT info

[Ho-Ren (Jack) Chuang]

* Introduce `mt_init_with_hmat()`
We defer memory tier initialization for those CPUless NUMA nodes
until acquiring HMAT info. `mt_init_with_hmat()` is introduced to
post-create CPUless memory tiers after obtaining HMAT info.
It iterates through each CPUless memory node, creating memory tiers if
necessary. Finally, it calculates demotion tables again at the end.

* Introduce `hmat_find_alloc_memory_type()`
Find or allocate a memory type in the `hmat_memory_types` list.

* Make `set_node_memory_tier()` more generic
This function can also be used for setting other memory types for a node.
To do so, a new argument is added to specify a memory type.

* Handle cases where there is no HMAT when creating memory tiers
If no HMAT is specified, it falls back to using `default_dram_type`.

* Change adist calculation code to use another new lock, mt_perf_lock.
Iterating through CPUlist nodes requires holding the `memory_tier_lock`.
However, `mt_calc_adistance()` will end up trying to acquire the same lock,
leading to a potential deadlock. Therefore, we propose introducing a
standalone `mt_perf_lock` to protect `default_dram_perf`. This approach not
only avoids deadlock but also prevents holding a large lock simultaneously.

Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@xxxxxxxxxxxxx>
Signed-off-by: Hao Xiang <hao.xiang@xxxxxxxxxxxxx>
---
 drivers/acpi/numa/hmat.c     |  3 ++
 include/linux/memory-tiers.h |  6 +++
 mm/memory-tiers.c            | 76 ++++++++++++++++++++++++++++++++----
 3 files changed, 77 insertions(+), 8 deletions(-)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index d6b85f0f6082..9f57338b3cb5 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -1038,6 +1038,9 @@ static __init int hmat_init(void)
 	if (!hmat_set_default_dram_perf())
 		register_mt_adistance_algorithm(&hmat_adist_nb);
 
+	/* Post-create CPUless memory tiers after getting HMAT info */
+	mt_init_with_hmat();
+
 	return 0;
 out_put:
 	hmat_free_structures();
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 69e781900082..2f845e90c033 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -48,6 +48,7 @@ int mt_calc_adistance(int node, int *adist);
 int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source);
 int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
+void mt_init_with_hmat(void);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -136,5 +137,10 @@ static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adis
 {
 	return -EIO;
 }
+
+static inline void mt_init_with_hmat(void)
+{
+
+}
 #endif	/* CONFIG_NUMA */
 #endif  /* _LINUX_MEMORY_TIERS_H */
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 0537664620e5..7a0a579b3deb 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -35,7 +35,9 @@ struct node_memory_type_map {
 };
 
 static DEFINE_MUTEX(memory_tier_lock);
+static DEFINE_MUTEX(mt_perf_lock);
 static LIST_HEAD(memory_tiers);
+static LIST_HEAD(hmat_memory_types);
 static struct node_memory_type_map node_memory_types[MAX_NUMNODES];
 struct memory_dev_type *default_dram_type;
 
@@ -502,7 +504,7 @@ static inline void __init_node_memory_type(int node, struct memory_dev_type *mem
 	}
 }
 
-static struct memory_tier *set_node_memory_tier(int node)
+static struct memory_tier *set_node_memory_tier(int node, struct memory_dev_type *new_memtype)
 {
 	struct memory_tier *memtier;
 	struct memory_dev_type *memtype;
@@ -514,7 +516,7 @@ static struct memory_tier *set_node_memory_tier(int node)
 	if (!node_state(node, N_MEMORY))
 		return ERR_PTR(-EINVAL);
 
-	__init_node_memory_type(node, default_dram_type);
+	__init_node_memory_type(node, new_memtype);
 
 	memtype = node_memory_types[node].memtype;
 	node_set(node, memtype->nodes);
@@ -623,6 +625,56 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype)
 }
 EXPORT_SYMBOL_GPL(clear_node_memory_type);
 
+static struct memory_dev_type *hmat_find_alloc_memory_type(int adist)
+{
+	bool found = false;
+	struct memory_dev_type *mtype;
+
+	list_for_each_entry(mtype, &hmat_memory_types, list) {
+		if (mtype->adistance == adist) {
+			found = true;
+			break;
+		}
+	}
+	if (!found) {
+		mtype = alloc_memory_type(adist);
+		if (!IS_ERR(mtype))
+			list_add(&mtype->list, &hmat_memory_types);
+	}
+	return mtype;
+}
+
+static void mt_create_with_hmat(int node)
+{
+	struct memory_dev_type *mtype = NULL;
+	int adist = MEMTIER_ADISTANCE_DRAM;
+
+	mt_calc_adistance(node, &adist);
+	if (adist != MEMTIER_ADISTANCE_DRAM) {
+		mtype = hmat_find_alloc_memory_type(adist);
+		if (IS_ERR(mtype))
+			pr_err("%s() failed to allocate a tier\n", __func__);
+	} else {
+		mtype = default_dram_type;
+	}
+
+	set_node_memory_tier(node, mtype);
+}
+
+void mt_init_with_hmat(void)
+{
+	int nid;
+
+	mutex_lock(&memory_tier_lock);
+	for_each_node_state(nid, N_MEMORY)
+		if (!node_state(nid, N_CPU))
+			mt_create_with_hmat(nid);
+
+	establish_demotion_targets();
+	mutex_unlock(&memory_tier_lock);
+}
+EXPORT_SYMBOL_GPL(mt_init_with_hmat);
+
 static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix)
 {
 	pr_info(
@@ -636,7 +688,7 @@ int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 {
 	int rc = 0;
 
-	mutex_lock(&memory_tier_lock);
+	mutex_lock(&mt_perf_lock);
 	if (default_dram_perf_error) {
 		rc = -EIO;
 		goto out;
@@ -684,7 +736,7 @@ int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 	}
 
 out:
-	mutex_unlock(&memory_tier_lock);
+	mutex_unlock(&mt_perf_lock);
 	return rc;
 }
 
@@ -700,7 +752,7 @@ int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 	    perf->read_bandwidth + perf->write_bandwidth == 0)
 		return -EINVAL;
 
-	mutex_lock(&memory_tier_lock);
+	mutex_lock(&mt_perf_lock);
 	/*
 	 * The abstract distance of a memory node is in direct proportion to
 	 * its memory latency (read + write) and inversely proportional to its
@@ -713,7 +765,7 @@ int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 		(default_dram_perf.read_latency + default_dram_perf.write_latency) *
 		(default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) /
 		(perf->read_bandwidth + perf->write_bandwidth);
-	mutex_unlock(&memory_tier_lock);
+	mutex_unlock(&mt_perf_lock);
 
 	return 0;
 }
@@ -797,7 +849,7 @@ static int __meminit memtier_hotplug_callback(struct notifier_block *self,
 		break;
 	case MEM_ONLINE:
 		mutex_lock(&memory_tier_lock);
-		memtier = set_node_memory_tier(arg->status_change_nid);
+		memtier = set_node_memory_tier(arg->status_change_nid, default_dram_type);
 		if (!IS_ERR(memtier))
 			establish_demotion_targets();
 		mutex_unlock(&memory_tier_lock);
@@ -836,7 +888,15 @@ static int __init memory_tier_init(void)
 	 * types assigned.
 	 */
 	for_each_node_state(node, N_MEMORY) {
-		memtier = set_node_memory_tier(node);
+		if (!node_state(node, N_CPU))
+			/*
+			 * Defer memory tier initialization on CPUless numa nodes.
+			 * These will be initialized when HMAT information is
+			 * available.
+			 */
+			continue;
+
+		memtier = set_node_memory_tier(node, default_dram_type);
 		if (IS_ERR(memtier))
 			/*
 			 * Continue with memtiers we are able to setup
-- 
Hao Xiang and Ho-Ren (Jack) Chuang